Yawen Wang

Papers

Total Citations

H-Index

About

Yawen Wang is a computer vision researcher whose work centers on manifold learning and its application to 3D reconstruction from high-dimensional visual data. Her key contribution lies in optimizing manifold learning techniques—such as Isomap, Locally Linear Embedding (LLE), Laplacian Eigenmaps, and t-SNE—by integrating differential geometry to preserve intrinsic structural properties during dimensionality reduction. This approach enables more accurate and robust 3D reconstruction, addressing a fundamental challenge in computer vision: how to extract meaningful lower-dimensional representations without losing critical geometric information. Wang’s most-cited paper, “Optimization of Manifold Learning Using Differential Geometry for 3D Reconstruction in Computer Vision” (2025, 1 citation), introduces a novel framework that bridges theoretical geometry and practical vision tasks, offering a pathway to improved performance in applications like autonomous navigation, medical imaging, and augmented reality. Though early in her citation impact, her work signals a promising direction for advancing manifold-based methods in computer vision. Wang’s research is particularly valuable for students and researchers seeking to understand how geometric principles can enhance machine learning pipelines for complex visual data.